Reviewer 1: Thank you for the insightful analysis and acknowledgement of our effort. We will split the table to improve readability and test data. The model is clearly expressive enough as training and test accuracy are near-perfect. Reviewer 3: 1. XMC datasets have been well-researched and improvements "by couple of % points" are significant. In Sec 2.2 and Theorem 2.1, we rigorously showed the existence of a perfect accuracy For example, compare P@k and PSP@k of PfastreXML and FastXML in Table 3 and Table 4.

Continuous action spaces in reinforcement learning (RL) are commonly defined as multidimensional intervals. While intervals usually reflect the action boundaries for tasks well, they can be challenging for learning because the typically large global action space leads to frequent exploration of irrelevant actions. Yet, little task knowledge can be sufficient to identify significantly smaller state-specific sets of relevant actions. Focusing learning on these relevant actions can significantly improve training efficiency and effectiveness. In this paper, we propose to focus learning on the set of relevant actions and introduce three continuous action masking methods for exactly mapping the action space to the state-dependent set of relevant actions. Thus, our methods ensure that only relevant actions are executed, enhancing the predictability of the RL agent and enabling its use in safety-critical applications. We further derive the implications of the proposed methods on the policy gradient. Using proximal policy optimization (PPO), we evaluate our methods on four control tasks, where the relevant action set is computed based on the system dynamics and a relevant state set. Our experiments show that the three action masking methods achieve higher final rewards and converge faster than the baseline without action masking.

We'd like to thank all the reviewers for your time and your constructive comments. One is a classical nonstationary Gaussian process regression: Paciorek et al. "Nonstationary The other is Heinonen et al. In particular, since Heinonen et al. can only model univariate observations, we have to As in Tables 1 and 2, both methods are inferior to ours, but Heinonen et al. method is comparable to the partition-based For Heinonen et al. method, we run 3 chains of 5000 samples of HMC-NUTS sampling to One major challenge to implement Paciorek et al. method is that the number of hyperparameters increases fast As suggested by R3, we plot the RMSE vs. Gibbs samples in Figure 1 We'll add these results to the camera-ready version. Chinese restaurant process will be our future work.

There is some knowledge from anatomy (Harris, et al, 2019).

With the increasing complexity of generative AI models, post-training quantization (PTQ) has emerged as a promising solution for deploying hyper-scale models on edge devices such as mobile and TVs. Existing PTQ schemes, however, consume considerable time and resources, which could be a bottleneck in real situations where frequent model updates and multiple hyperparameter tunings are required. As a cost-effective alternative, learning-free PTQ schemes have been proposed. However, the performance is somewhat limited because they cannot consider the inter-layer dependency within the attention module, which is a significant feature of Transformers. In this paper, we thus propose a novel PTQ algorithm that balances accuracy and efficiency. The key idea of the proposed algorithm called aespa is to perform quantization layer-wise for efficiency while targeting attention-wise reconstruction to consider the cross-layer dependency. Through extensive experiments on various language models and complexity analysis, we demonstrate that aespa is accurate and efficient in quantizing Transformer models.

We thank all reviewers for their valuable comments, such as the novelty, well-motivated objective and promising results. The code "ICP-pytorch" has been anonymously released on GitHub. We rebut key issues point-by-point as below. We sincerely hope R#2 to raise the score. We rebut these concerns below, and will clarify related issues in our paper.

In this paper, we reconstruct naturalistic images directly from macaque brain signals using a convolutional neural network (CNN) based decoder. We investigate the ability of this CNN-based decoding technique to differentiate among neuronal populations from areas V1, V4, and IT, revealing distinct readout characteristics for each. This research marks a progression from low-level to high-level brain signals, thereby enriching the existing framework for utilizing CNN-based decoders to decode brain activity. Our results demonstrate high-precision reconstructions of naturalistic images, highlighting the efficiency of CNN-based decoders in advancing our knowledge of how the brain's representations translate into pixels. Additionally, we present a novel space-time-resolved decoding technique, demonstrating how temporal resolution in decoding can advance our understanding of neural representations. Moreover, we introduce a learned receptive field layer that sheds light on the CNN-based model's data processing during training, enhancing understanding of its structure and interpretive capacity.

State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks. Learning such representations without supervision from rewards is a challenging open problem. We introduce a method that learns state representations by maximizing mutual information across spatially and temporally distinct features of a neural encoder of the observations. We also introduce a new benchmark based on Atari 2600 games where we evaluate representations based on how well they capture the ground truth state variables. We believe this new framework for evaluating representation learning models will be crucial for future representation learning research. Finally, we compare our technique with other state-of-the-art generative and contrastive representation learning methods.

Mechanistic interpretability methods aim to identify the algorithm a neural network implements, but it is difficult to validate such methods when the true algorithm is unknown.

Mechanistic interpretability methods aim to identify the algorithm a neural network implements, but it is difficult to validate such methods when the true algorithm is unknown.